AquaVision3D: Physically-Consistent Medium Modelling for Underwater Gaussian Splatting

Giri, Kaushlendra Kumar, Bian, Shaojun, Ihmeida, Mohamed, Wu, Yun and Tharib, Safa (2026) AquaVision3D: Physically-Consistent Medium Modelling for Underwater Gaussian Splatting. In: UniWorld Workshop @ ECCV2026: Universal Representations for Perception, Reasoning, and World Modeling, 28-30 July 2026, Cardiff, United Kingdom.

Full text not available from this repository. (Request a copy)

Access this via: https://openreview.net/forum?id=u9UwMP2u33

Abstract

Underwater 3D scene reconstruction is challenging because wavelength-dependent attenuation, backscatter, and depth-dependent color shift cause photometric inconsistency across images. Existing medium-field methods condition on ray direction, assigning the same medium to every scene point along a ray and failing to capture spatial variation with depth. We present AquaVision3D, which instead conditions the medium on each Gaussian’s world-space position using a multi-resolution hash grid (instant-NGP), enabling spatially-varying attenuation, backscatter, and veiling-light parameters. We identify and fix a critical training collapse caused by an optimizer reset designed for MLPs, and we address channel imbalance and bounding-box sensitivity with practical tuning. Beyond outperforming vanilla 3D Gaussian Splatting (3DGS), AquaVision3D establishes a new spatial foundation for underwater medium modeling. While currently competitive with direction-conditioned methods on five of six scenes, the remaining gap explicitly reveals that angular scattering effects are complementary to spatial information, pointing toward a hybrid spatial-angular representation that our framework is well-positioned to adopt.

Item Type:	Conference or Workshop Item (Paper)
Keywords:	Underwater 3D Reconstruction, 3D Gaussian Splatting, Neural Scene Representations, Position-Conditioned Medium Fields, Multi-resolution Hash Encoding
Divisions:	College of Creative Arts, Technology and Engineering
Depositing User:	Jessie McLean
Date Deposited:	05 Oct 2026 14:25
Last Modified:	05 Oct 2026 15:43
URI:	https://bnu.repository.guildhe.ac.uk/id/eprint/21792

Actions (login required)

Edit Item